© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96517
    Prev
    Next
    INDEX
    Explanations

    technical information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¿¡
    -0.52
     envelope
    -0.36
     folder
    -0.35
     Album
    -0.35
    folder
    -0.35
    å°ģ
    -0.33
     album
    -0.33
    è´´
    -0.33
     A
    -0.32
     folders
    -0.32
    POSITIVE LOGITS
    æĭħ
    0.27
     Yük
    0.26
     Jeb
    0.25
    ç®±
    0.25
    è·ª
    0.25
     Tucker
    0.25
    _critical
    0.25
    çŃIJ
    0.24
     box
    0.24
     Wend
    0.24
    Activations Density 0.922%

    No Known Activations